opendatalab models

2 opendatalab models from opendatalab on Hugging Face, from 1.2B to 1.2B parameters, published by opendatalab in BF16, with contexts from 16K to 32K tokens. The smallest official model, MinerU2.5-2509-1.2B, needs about 2.6 GB of VRAM at its published precision; the cheapest live fit is RTX 3070 at $0.088/hr.

Pick a size

One row per official opendatalab size: the VRAM it needs at each precision, the cheapest GPU that holds it today, and the KV cache for a 32K-token context.

ModelParametersNative VRAMFP8 VRAMINT4 VRAMLive GPU fit (native)Est. $/hrKV cache at 32K
MinerU2.5-Pro-2604-1.2B1.2B2.6 GB1.3 GB0.6 GBRTX 3070$0.088/hr0.38 GB

VRAM is weights times a flat 1.2 overhead; the KV cache is a separate per-model figure at 16-bit, shown where the architecture is published. See the methodology.

Official models (2)

ModelParametersPublished asVRAM neededLive GPU fitEst. $/hr
MinerU2.5-2509-1.2B1.2BBF162.6 GBRTX 3070$0.088/hr
MinerU2.5-Pro-2604-1.2B1.2BBF162.6 GBRTX 3070$0.088/hr

VRAM is for the precision the model is published in: the weights times a flat 1.2 overhead, with the KV cache not included. See the methodology. The fit shown is the lowest-priced single GPU type that holds the model at that precision, or the lowest-priced multi-GPU set (up to 8) when none does.

Start ComfyUI on a rented GPU.

© 2026 Aquanode. All rights reserved.

All trademarks, logos and brand names are the property of their respective owners.